Browsing Computer Science and Artificial Intelligence Lab (CSAIL) by Subject "effective dimension"
Now showing items 1-2 of 2
-
Empirical Effective Dimension and Optimal Rates for Regularized Least Squares Algorithm
(2005-05-27)This paper presents an approach to model selection for regularized least-squares on reproducing kernel Hilbert spaces in the semi-supervised setting. The role of effective dimension was recently shown to be crucial in the ...
-
Risk Bounds for Regularized Least-squares Algorithm with Operator-valued kernels
(2005-05-16)We show that recent results in [3] on risk bounds for regularized least-squares on reproducing kernel Hilbert spaces can be straightforwardly extended to the vector-valued regression setting. We first briefly introduce ...